Citizen-centric digital twin development with machine learning and interfaces for maintaining urban infrastructure

Abstract

Serious interoperability challenges prevent the stakeholders of infrastructure projects and citizens as the final users, from interacting with each other and helping maintain a project over its lifetime. This paper focuses on macro-scale digital twins collecting stakeholders’ feedback as the end users of the infrastructure and its service buildings. The aim is to examine various technologies for developing a CCDT and use the information processed to maintain and manage infrastructure services. This involves a systematic review, investigating technologies for data acquisition, data processing, and interface development to improve CCDT capabilities. Among the 89 selected articles, 16% of the sample dataset directly focused on users’ engagement. When considering data acquisition technologies, the open data platforms (37% of the sample dataset), remote sensors (37%), and IoT sensors (8%) ensure the dynamic capabilities of the digital twin. Volunteered geographic information (VGI) and social sensing are two prominent technologies that encourage citizen engagement. The number of articles considering the use of segmentation and classification and object detection and tracking algorithms at city-scale digital twins is significant, accounting for 25% and 24% of all articles discussing various algorithms. Further, the study carried out a comprehensive analysis of application programming interfaces (APIs) while presenting their specifications, features, and applications.